skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: DEEP Picker is a Deep Neural Network for Accurate Deconvolution of Complex Two-Dimensional NMR Spectra
The analysis of nuclear magnetic resonance (NMR) spectra for the comprehensive and unambiguous identification and characterization of peaks is a difficult, but critically important step in all NMR analyses of complex biological molecular systems. Here, we introduce DEEP Picker, a deep neural network (DNN)-based approach for peak picking and spectral deconvolution which semi-automates the analysis of two-dimensional NMR spectra. DEEP Picker includes 8 hidden convolutional layers and was trained on a large number of synthetic spectra of known composition with variable degrees of crowdedness. We show that our method is able to correctly identify overlapping peaks, including ones that are challenging for expert spectroscopists and existing computational methods alike. We demonstrate the utility of DEEP Picker on NMR spectra of folded and intrinsically disordered proteins as well as a complex metabolomics mixture, and show how it provides access to valuable NMR information. DEEP Picker should facilitate the semi-automation and standardization of protocols for better consistency and sharing of results within the scientific community.  more » « less
Award ID(s):
2103637
PAR ID:
10332410
Author(s) / Creator(s):
; ; ; ;
Date Published:
Journal Name:
Nature communications
ISSN:
2041-1723
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; ; ; ; (, Phys. Chem. Chem. Phys.)
    We demonstrate that natural isotopic abundance 2D heteronuclear correlation (HETCOR) solid-state NMR spectra can be used to significantly reduce or eliminate the broadening of 1 H and 13 C solid-state NMR spectra of organic solids due to anisotropic bulk magnetic susceptibility (ABMS). ABMS often manifests in solids with aromatic groups, such as active pharmaceutical ingredients (APIs), and inhomogeneously broadens the NMR peaks of all nuclei in the sample. Inhomogeneous peaks with full widths at half maximum (FWHM) of ∼1 ppm typically result from ABMS broadening and the low spectral resolution impedes the analysis of solid-state NMR spectra. ABMS broadening of solid-state NMR spectra has previously been eliminated using 2D multiple-quantum correlation experiments, or by performing NMR experiments on diluted materials or single crystals. However, these experiments are often infeasible due to their poor sensitivity and/or provide limited gains in resolution. 2D 1 H– 13 C HETCOR experiments have previously been applied to reduce susceptibility broadening in paramagnetic solids and we show that this strategy can significantly reduce ABMS broadening in diamagnetic organic solids. Comparisons of 1D solid-state NMR spectra and 1 H and 13 C solid-state NMR spectra obtained from 2D 1 H– 13 C HETCOR NMR spectra show that the HETCOR spectrum directly increases resolution by a factor of 1.5 to 8. The direct gain in resolution is determined by the ratio of the inhomogeneous 13 C/ 1 H linewidth to the homogeneous 1 H linewidth, with the former depending on the magnitude of the ABMS broadening and the strength of the applied field and the latter on the efficiency of homonuclear decoupling. The direct gains in resolution obtained using the 2D HETCOR experiments are better than that obtained by dilution. For solids with long proton longitudinal relaxation times, dynamic nuclear polarization (DNP) was applied to enhance sensitivity and enable the acquisition of 2D 1 H– 13 C HETCOR NMR spectra. 2D 1 H– 13 C HETCOR experiments were applied to resolve and partially assign the NMR signals of the form I and form II polymorphs of aspirin in a sample containing both forms. These findings have important implications for ultra-high field NMR experiments, optimization of decoupling schemes and assessment of the fundamental limits on the resolution of solid-state NMR spectra. 
    more » « less
  2. ; (, Metabolites)
    Background: Quantification of metabolites from nuclear magnetic resonance (NMR) spectra in an accurate, high-throughput manner requires effective data processing tools. Neural networks are relatively underexplored in quantitative NMR metabolomics despite impressive speed and throughput compared to more conventional peak-fitting metabolomics software. Methods: This work investigates practices for dataset and model development in the task of metabolite quantification directly from simulated NMR spectra for three neural network models: the multi-layered perceptron, the convolutional neural network, and the transformer. Model architectures, training parameters, and training datasets are optimized before comparing each model on simulated 400-MHz 1H-NMR spectra of complex mixtures with 8, 44, or 86 metabolites to quantify in spectra ranging from simple to highly complex and overlapping peaks. The optimized models were further validated on spectra at 100- and 800-MHz. Results: The transformer was the most effective network for NMR metabolite quantification, especially as the number of metabolites per spectra increased or target concentrations were low or had a large dynamic range. Further, the transformer was able to accurately quantify metabolites in simulated spectra from 100-MHz up to 800-MHz. Conclusions: The methods developed in this work reveal that transformers have the potential to accurately perform fully automated metabolite quantification in real-time and, with further development with experimental data, could be the basis for automated quantitative NMR metabolomics software. 
    more » « less
  3. ; ; (, Applied Sciences)
    Solid-state nuclear magnetic resonance (ssNMR) spectroscopy enables studying complex macromolecules with low solubility. Compared to solution NMR, few tools exist for biomacromolecule ssNMR data analysis. A key challenge is assigning spin systems due to low peak dispersion. Broad peaks from large dipolar couplings and shift anisotropy cause significant overlap and missing peaks. To address this, we introduce ssPINE-POKY, a user-friendly graphical user interface (GUI) integrated into the POKY suite. ssPINE-POKY streamlines the automation of spin system recognition and chemical shift assignment in multidimensional ssNMR spectra by integrating the ssPINE algorithm within an intuitive interface. The platform allows easy and fast job submission, real-time result visualization, and enhanced analysis through additional built-in tools, significantly improving the efficiency of ssNMR data interpretation. 
    more » « less
  4. ; ; ; ; (, Journal of Biomolecular NMR)
    Abstract Rapid progress in machine learning offers new opportunities for the automated analysis of multidimensional NMR spectra ranging from protein NMR to metabolomics applications. Most recently, it has been demonstrated how deep neural networks (DNN) designed for spectral peak picking are capable of deconvoluting highly crowded NMR spectra rivaling the facilities of human experts. Superior DNN-based peak picking is one of a series of critical steps during NMR spectral processing, analysis, and interpretation where machine learning is expected to have a major impact. In this perspective, we lay out some of the unique strengths as well as challenges of machine learning approaches in this new era of automated NMR spectral analysis. Such a discussion seems timely and should help define common goals for the NMR community, the sharing of software tools, standardization of protocols, and calibrate expectations. It will also help prepare for an NMR future where machine learning and artificial intelligence tools will be common place. 
    more » « less
  5. ; ; ; ; ; (, Geophysical Journal International)
    SUMMARY Applications of machine learning in seismology have greatly improved our capability of detecting earthquakes in large seismic data archives. Most of these efforts have been focused on continental shallow earthquakes, but here we introduce an integrated deep-learning-based workflow to detect deep earthquakes recorded by a temporary array of ocean-bottom seismographs (OBSs) and land-based stations in the Tonga subduction zone. We develop a new phase picker, PhaseNet-TF, to detect and pick P- and S-wave arrivals in the time–frequency domain. The frequency-domain information is critical for analysing OBS data, particularly the horizontal components, because they are contaminated by signals of ocean-bottom currents and other noise sources in certain frequency bands. PhaseNet-TF shows a much better performance in picking S waves at OBSs and land stations compared to its predecessor PhaseNet. The predicted phases are associated using an improved Gaussian Mixture Model Associator GaMMA-1D and then relocated with a double-difference package teletomoDD. We further enhance the model performance with a semi-supervised learning approach by iteratively refining labelled data and retraining PhaseNet-TF. This approach effectively suppresses false picks and significantly improves the detection of small earthquakes. The new catalogue of Tonga deep earthquakes contains more than 10 times more events compared to the reference catalogue that was analysed manually. This deep-learning-enhanced catalogue reveals Tonga seismicity in unprecedented detail, and better defines the lateral extent of the double-seismic zone at intermediate depths and the location of four large deep-focus earthquakes relative to background seismicity. It also offers new potential for deciphering deep earthquake mechanisms, refining tomographic models, and understanding of subduction processes. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email